Search Results for author: Radu Marinescu

Found 11 papers, 1 papers with code

Finding Sub-task Structure with Natural Language Instruction

no code implementations LNLS (ACL) 2022 Ryokan Ri, Yufang Hou, Radu Marinescu, Akihiro Kishimoto

When mapping a natural language instruction to a sequence of actions, it is often useful toidentify sub-tasks in the instruction.

Boolean Decision Rules for Reinforcement Learning Policy Summarisation

no code implementations18 Jul 2022 James McCarthy, Rahul Nair, Elizabeth Daly, Radu Marinescu, Ivana Dusparic

Explainability of Reinforcement Learning (RL) policies remains a challenging research problem, particularly when considering RL in a safety context.

reinforcement-learning reinforcement Learning

Contrastive Explanations for Comparing Preferences of Reinforcement Learning Agents

no code implementations17 Dec 2021 Jasmina Gajcin, Rahul Nair, Tejaswini Pedapati, Radu Marinescu, Elizabeth Daly, Ivana Dusparic

In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, but employ different strategies can be trained by adjusting the impact of individual objectives on reward function.

Autonomous Driving reinforcement-learning +1

Logical Credal Networks

no code implementations25 Sep 2021 Haifeng Qian, Radu Marinescu, Alexander Gray, Debarun Bhattacharjya, Francisco Barahona, Tian Gao, Ryan Riegel, Pravinda Sahu

This paper introduces Logical Credal Networks, an expressive probabilistic logic that generalizes many prior models that combine logic and probability.

Designing Machine Learning Pipeline Toolkit for AutoML Surrogate Modeling Optimization

1 code implementation2 Jul 2021 Paulito P. Palmes, Akihiro Kishimoto, Radu Marinescu, Parikshit Ram, Elizabeth Daly

The pipeline optimization problem in machine learning requires simultaneous optimization of pipeline structures and parameter adaptation of their elements.

AutoML BIG-bench Machine Learning +1

Counting the Optimal Solutions in Graphical Models

no code implementations NeurIPS 2019 Radu Marinescu, Rina Dechter

We introduce #opt, a new inference task for graphical models which calls for counting the number of optimal solutions of the model.

From Stochastic Planning to Marginal MAP

no code implementations NeurIPS 2018 Hao Cui, Radu Marinescu, Roni Khardon

This yields a novel algebraic gradient-based solver (AGS) for MMAP.

Parallel Recursive Best-First AND/OR Search for Exact MAP Inference in Graphical Models

no code implementations NeurIPS 2015 Akihiro Kishimoto, Radu Marinescu, Adi Botea

The paper presents and evaluates the power of parallel search for exact MAP inference in graphical models.

AND/OR Multi-Valued Decision Diagrams (AOMDDs) for Graphical Models

no code implementations15 Jan 2014 Robert Mateescu, Rina Dechter, Radu Marinescu

We provide two algorithms for compiling the AOMDD of a graphical model.

Cannot find the paper you are looking for? You can Submit a new open access paper.